Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaGo beats Lee Sedol again in match 2 of 5

gogameguru.com

Post reply on HN
Print view View original

551–560 of 576 posts

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#551

Post by taneq »

thevibesman wrote: post #444
taneq wrote: post #224

Earlier quoted context omitted.

There was one move that literally caused the 9th dan commentator to do a triple-take. It apparently turned out to be super effective.

Not only did the commentator do a triple-take, but the next white move took Sedol about 15 minutes. One interesting thing that happened during the time for Sedol's next move was that the 9th dan commentator started referring to AlphaGo as "he".

Yeah, I've been noticing the pronouns thing. In chess challenges I always got the impression that the AI's play style was like a chain chomp. Limited, but ruthless within its limits, and definitely 'mechanical'. In these games the commentators are treating AlphaGo like a person.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#552

Post by kerkeslager »

As a programmer and a go player, I knew this day would come, but I'm a bit disappointed that this is how it happened, for two reasons:

1. As the game of go progresses, the number of reasonable moves decreases, so that as the game progresses, players on average play closer and closer to optimally. By the end of the game, even weak amateurs can calculate the optimal move. Logically, I would guess that stronger players are able to play optimally earlier than weak ones. Lee Sedol is known for his strong middle and endgame, often falling behind early on and making it up late in the game. He is so strong at this that he has driven an entire generation of go players to developing very strong endgame. But AlphaGo, running Monte Carlo simulations, almost certainly can brute force the game earlier than Lee Sedol can. Lee Sedol is playing AlphaGo on its own turf. A player known for their opening prowess, such as Kobayashi Koichi in his heyday, might have had an advantage that Lee Sedol doesn't. (Note: I'm not strong enough to analyze Lee Sedol or Kobayashi Koichi's play styles; I'm repeating what I've heard from professionals.)

2. I hoped that when an AI beat a pro at go, it would be with a more adaptive algorithm, one not specifically designed to play go. If my understanding of AlphaGo is correct, it's basically just Monte Carlo: the advances made were primarily in improving the scoring function to be more accurate earlier, and the tree pruning function, both of which are go-specific. It's not really a new way of thinking about go (at least, since Monte Carlo was first applied to go). It's just an old way optimized. The AI can't, for example, explain its moves, or apply what it learned from learning go to another game. It's certainly a milestone in Go AI, and I don't want to downplay what an achievement this is for the AlphaGo developers, but I also don't think this is the progress toward a more generalized AI that I hoped would be the first to beat a professional.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#553

Post by kerkeslager »

z0r wrote: post #513
zeven7 wrote: post #507

Earlier quoted context omitted.

It didn't look like a Takemiya-style move to me. Takemiya tends to play for a huge moyo in the center. AlphaGo had no such moyo. It wasn't only a strange move; it was also a strange time to play it, and it definitely went against conventional wisdom.

The result of the shoulder hit coordinated with black's bottom formation, and the extension on the 4th line that threatened to cut white's stones off was flexible and could have easily formed an impressive moyo on the bottom. It did not play out that way, but I think that black's strategy was as cosmic as anything Takemiya might have played. His games did not always end with a giant moyo, he was also very flexible. I…

Those games are really interesting. In the first two, they are both ladder-breakers played by stronger players; my guess is the weaker players set up the ladders assuming that the stronger players wouldn't play a fifth line shoulder hit to break them, and the stronger player didn't back down. In the third game, the fifth line shoulder hits aren't that surprising; they're reductions against frameworks that were allowed to get big in exchange for growing an opposing framework; they're locally bad moves but the global benefits are clear; you'll note that both players play a fifth line shoulder hit.

The only one I can't parse is the last one. There are a lot of variations where I want to know what black's plan is.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#554

Post by anabis »

Jach wrote: post #249
taneq wrote: post #232

Earlier quoted context omitted.

I find it interesting that people are using gendered pronouns for AlphaGo. Getting some definite Turing-test vibes here.

Myungwan Kim said he feels like it plays like a she. Personally I think its informal gender was determined by the nigiri of the first match, as it's common to refer to black as he and white as she absent of player names. And I'm expecting to see at least one really cute AlphaGo-tan drawing any day now.

Here you go:

https://twitter.com/zpdldlfrkwl/status/707858454317178880

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#555

Post by versteegen »

kerkeslager wrote: post #552

As a programmer and a go player, I knew this day would come, but I'm a bit disappointed that this is how it happened, for two reasons: 1. As the game of go progresses, the number of reasonable moves decreases, so that as the game progresses, players on average play closer and closer to optimally. By the end of the game, even weak amateurs can calculate the optimal move. Logically, I would guess that stronger players…

> I hoped that when an AI beat a pro at go, it would be with a more adaptive algorithm, one not specifically designed to play go.

The particular algorithm used by AlphaGo is of course specific to Go (the neural network inputs have a number of hand-crafted features), but the overall structure of the algorithm - MCTS, deep neural nets, reinforcement learning - is very general. So there's two ways to look at it. One is that what you wanted has actually transpired.

The other is that what you asked for is completely unreasonable. I think it highly unlikely that an algorithm not specialised to Go will ever be able to beat all specialist Go playing programs.

AlphaGo can't explain the outputs of its two NNs, but it can still explain its moves by showing which variations it thinks are likely.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#556

Post by Findy3ti »

anabis wrote: post #554
Jach wrote: post #249

Earlier quoted context omitted.

Myungwan Kim said he feels like it plays like a she. Personally I think its informal gender was determined by the nigiri of the first match, as it's common to refer to black as he and white as she absent of player names. And I'm expecting to see at least one really cute AlphaGo-tan drawing any day now.

Here you go: https://twitter.com/zpdldlfrkwl/status/707858454317178880

A little NSFW. Was expecting cartoon cute instead got cartoon sexy

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#557

Post by ig1 »

zardeh wrote: post #496
ig1 wrote: post #254

Earlier quoted context omitted.

AlphaGo is essentially built on the work that IBM did on TD-Gammon (a reinforcement learning backgammon player) in the 90s. Pretty much the same thing happened with TD-Gammon with it playing unconventional moves, in the longer term humans ended up adopting some of TD-Gammon's tactics once they understood how they played out, it wouldn't be surprising to see the same happen with Go.

Reading the paper, it doesn't at all sound like AlphaGo uses anything that TD-Gammon used. It uses MCTS, which is unlike minimax. It doesn't use temporal difference learning, although they say that the policy somewhat resembles TD. That doesn't sound like 'essentially built on', its sounds maybe like 'slightly influenced by'

You're missing the forest for the trees.

Tesauro's work on TD-Gammon was pioneering at the high level, i.e. combining reinforcement learning + self-play + neural networks.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#558

Post by EliRivers »

botw wrote: post #400
EliRivers wrote: post #255

Earlier quoted context omitted.

So what? Doesn't change the facts. There is no child here. There is a set of deterministic calculations written by some people, and executed.

please give the definition for a set of deterministic calculations.

Are you serious? You want me to tell you what calculations are? Having trouble using google with those flippers, I expect.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#559

Post by pavelrub »

iopq wrote: post #416
pavelrub wrote: post #250

Earlier quoted context omitted.

Well, I guess it was more true before the advent of Monte Carlo Tree Search. Even so, note that even in the case of MoGoTW in 2011, it played blind Go (this helps the computer), and out of 4 games, won two games against a 9p player, and lost 1 game to a 5p player. Though it is perhaps better than MoGo's performance on 19x19, it still isn't very good, doesn't seem much better than MoGo on 13x13, and performs much wors…

The branching factor is much larger, around 75 legal moves after the opening, while chess has at most like 30. Fuego beat a pro in 2008 using MCTS actually.

The branching factor of 9x9 Go isn't 75. 75 could be the factor in early game, but the average factor is somewhere between 40 and 50, versus 35 in chess. State-space complexity is also considerably higher in Chess than in 9x9 Go.

Not sure what you meant regarding MCTS, I never said anything about MCTS not being able to beat pros.

Re: AlphaGo beats Lee Sedol again in match 2 of 5

#560

Post by kofejnik »

fma wrote: post #333
Ensorceled wrote: post #322

Earlier quoted context omitted.

> AlphaGo plays some unusual moves that go clearly against any classically trained Go players. Moves that simply don't quite fit into the current theories of Go playing, and the world's top players are struggling to explain what's the purpose/strategy behind them. Could AlphaGO be winning in a way similar to left handed fencers having an advantage over right handers by wrong footing them rather than simply being bett…

I'm not a Go player but play other competitive sports. Humans have a herd mentality...as Op mentioned there's certain styles of playing...which has their own strengths and weaknesses. Sometimes people will not examine other styles that may have better strengths and just focus on the exist one. Then comes along someone who 'thinks outside the box' with a new style and revolutionize the playing field. Think Bruce Lee a…

Bruce Lee played it very smart and attained a guru status in the West, but there's no evidence he was a world-class fighter, only unsubstantiated claims by his entourage.

As for JKD, people are drawn in by its oriental esotericism, but there's no evidence it is an especially effective fighting style, or that it has something that (kick)boxing does not.

Post reply on HN